© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 79439
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kut
    -0.07
     위해서
    -0.07
    [contains
    -0.07
     Prozent
    -0.07
    ยง
    -0.06
    	with
    -0.06
    ạo
    -0.06
    SETTINGS
    -0.06
     heeft
    -0.06
     macht
    -0.06
    POSITIVE LOGITS
     drawings
    0.07
     assembled
    0.07
     Simon
    0.07
    opup
    0.07
    ")
↵
    0.06
    Sketch
    0.06
    dep
    0.06
     instrumentation
    0.06
     Nano
    0.06
     multi
    0.06
    Activations Density 0.003%

    No Known Activations